Skip to content

Speed up uncompressed DDS reader #9943

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
akx wants to merge 2 commits into
base: main
Choose a base branch
from
+38 −17
Open

Speed up uncompressed DDS reader #9943

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
862c803
Benchmarks: split PATHS to LOAD_PATHS/SAVE_PATHS; benchmark uncompres…
akx Sep 2, 2026
57f358f
Speed up uncompressed DDS reading
akx Sep 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 8 additions & 4 deletions Tests/benchmarks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,9 +45,13 @@

# For benchmarks that act on test fixture files, these are the paths loaded.
IMAGES_PATH = pathlib.Path(__file__).parent / "images"
PATHS = [
SAVE_PATHS = [
IMAGES_PATH / "flower2.jpg",
]
LOAD_PATHS = [
*SAVE_PATHS,
IMAGES_PATH / "uncompressed_rgb.dds",
]

# These are derived from the other configuration, above.
RGB_MODES = [mode for mode in MODES if mode.startswith("RGB")]
Expand Down Expand Up @@ -567,7 +571,7 @@ def test_draw_lines_blend(


@pytest.mark.benchmark(group="load")
@pytest.mark.parametrize("path", PATHS, ids=_format_path)
@pytest.mark.parametrize("path", LOAD_PATHS, ids=_format_path)
def test_load(bench: BenchmarkFixture, path: pathlib.Path) -> None:
def run() -> None:
with Image.open(path) as im:
Expand All @@ -577,7 +581,7 @@ def run() -> None:


@pytest.mark.benchmark(group="save")
@pytest.mark.parametrize("path", PATHS, ids=_format_path)
@pytest.mark.parametrize("path", SAVE_PATHS, ids=_format_path)
def test_save_jpeg(bench: BenchmarkFixture, path: pathlib.Path) -> None:
with Image.open(path) as im:
im.load()
Expand Down Expand Up @@ -853,7 +857,7 @@ def test_quantize_grayscale_to_palette(
"source_type",
[
"synthetic",
*(pytest.param(image, id=f"{image.stem}") for image in PATHS),
*(pytest.param(image, id=f"{image.stem}") for image in LOAD_PATHS),
],
)
@pytest.mark.parametrize("palette_type", ["exact", "grayscale", "web"])
Expand Down
43 changes: 30 additions & 13 deletions src/PIL/DdsImagePlugin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,6 @@

from . import Image, ImageFile, ImagePalette
from ._binary import i32le as i32
from ._binary import o8
from ._binary import o32le as o32

TYPE_CHECKING = False
Expand Down Expand Up @@ -514,20 +513,38 @@ def decode(self, buffer: Image.DecoderInput) -> tuple[int, int]:
mask_totals.append(mask >> offset)

assert self.fd is not None
dest_length = self.state.xsize * self.state.ysize * len(masks)
while len(data) < dest_length:
bytes_read = self.fd.read(bytecount)
if len(bytes_read) < bytecount:
pixel_count = self.state.xsize * self.state.ysize

src = bytearray()
needed = pixel_count * bytecount
while len(src) < needed:
chunk = self.fd.read(min(needed - len(src), ImageFile.SAFEBLOCK))
if not chunk:
break
value = int.from_bytes(bytes_read, "little")
for i, mask in enumerate(masks):
masked_value = value & mask
src += chunk
pixel_count = min(pixel_count, len(src) // bytecount)

@radarhere radarhere Sep 5, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

len(src) // bytecount might be less if the image is truncated, but why would pixel_count ever be less? Why not always use len(src) // bytecount?

src_length = pixel_count * bytecount
del src[src_length:]

nmasks = len(masks)
data = bytearray(pixel_count * nmasks)
for i, (mask, offset, total) in enumerate(
zip(masks, mask_offsets, mask_totals)
):
if not total: # Nothing to do here
continue
if total == 0xFF and offset % 8 == 0: # Whole byte, fast path
data[i::nmasks] = src[offset // 8 :: bytecount]
continue
values = (
int.from_bytes(src[p : p + bytecount], "little")
for p in range(0, src_length, bytecount)
)
data[i::nmasks] = bytes(
# Remove the zero padding, and scale it to 8 bits
data += o8(
int(((masked_value >> mask_offsets[i]) / mask_totals[i]) * 255)
if mask_totals[i]
else 0
)
int((((value & mask) >> offset) / total) * 255)
for value in values
)
self.set_as_raw(data)
return -1, 0

Expand Down